Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond the readOnlyHint annotation, the description discloses that results are catalog estimates rather than measured or scanned data. 'Pas un scan, pas un benchmark, pas de tokens/s inventés' clearly sets expectations about output provenance and prevents overclaiming.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler. The core filter action is front-loaded, and the limitation statement is compact and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple and has an output schema, so return-value documentation is not necessary. However, with 5 parameters and no schema descriptions, omitting two of them makes the definition not fully self-sufficient. A sentence on unified_memory and storage_free_gb would close the gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description maps vram_gb, ram_gb, and usage into understandable language, but the schema itself has 0% parameter descriptions. It leaves unified_memory and storage_free_gb completely unexplained, so an agent gets no help understanding the boolean unified_memory flag or how storage_free_gb factors into filtering.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete action ('Filtre le catalogue public') with explicit filtering criteria (VRAM, optional RAM, usage). It also disambiguates from measurement/report tools by saying it is not a scan or benchmark, which distinguishes it from siblings like list_benchmark_proofs_from_report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says this is catalog-only estimation and not a scan, benchmark, or source of invented tokens/s, giving clear when-not guidance. It does not name sibling alternatives, so routing is less direct than it could be.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.